Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003736294802a15151f66f8e67f2e4706c410829601a7ecb1578474277867165
+oid sha256:7fcf4897bc77cb30e174f553e0fb979d3060a22013740f7b4fd53170bc37ca9a
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712483dcfe94bc060ec2acfd864831b36255af57775103f39f5c9eb61881b2f5
+oid sha256:29163dfd7463768137db499ee4e467be9a61499b9fc3f5ceec2df76d5636ff11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
+oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06768684389199352,
+  "epoch": 0.07520760432443725,
   "eval_steps": 50,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -590,6 +590,69 @@
       "learning_rate": 1.99258117923236e-05,
       "loss": 0.0,
       "step": 81
+    },
+    {
+      "epoch": 0.06852248394004283,
+      "grad_norm": NaN,
+      "learning_rate": 1.796955257999768e-05,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.06935812398809213,
+      "grad_norm": NaN,
+      "learning_rate": 1.6101230183944144e-05,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.07019376403614143,
+      "grad_norm": NaN,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.07102940408419073,
+      "grad_norm": NaN,
+      "learning_rate": 1.2639779077309098e-05,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.07186504413224004,
+      "grad_norm": NaN,
+      "learning_rate": 1.1051987673443085e-05,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.07270068418028934,
+      "grad_norm": NaN,
+      "learning_rate": 9.56279946954021e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.07353632422833864,
+      "grad_norm": NaN,
+      "learning_rate": 8.174510685872415e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.07437196427638794,
+      "grad_norm": NaN,
+      "learning_rate": 6.889261963118898e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.07520760432443725,
+      "grad_norm": NaN,
+      "learning_rate": 5.709035061653494e-06,
+      "loss": 0.0,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -609,7 +672,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.750672775859405e+16,
+  "total_flos": 7.500747528732672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null